INDEX

Explanations

instances of the keyword 'new', likely in a programming context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagHelper

-0.66

 snippetHide

-0.61

localVar

-0.60

posób

-0.55

Tracce

-0.55

帖最后由

-0.52

冒

-0.52

ము

-0.52

tumblr

-0.50

ituary

-0.50

POSITIVE LOGITS

IUrlHelper

0.81

DispatchToProps

0.79

]--;

0.78

 disambiguazione

0.77

AndroidJUnit

0.75

OGND

0.72

 وتسجيلات

0.68

StoryboardSegue

0.68

 wireType

0.67

Попис

0.65

Activations Density 0.076%

instances of the keyword 'new', likely in a programming context

No Comments

No Known Activations